Agent Lab — a live forecast exhibit · Applied AI
← Schedule
Group B · Matchday 8 · 2026-06-18

Switzerland vs Bosnia and Herzegovina

Inglewood, United States · neutral venue

Full time SUI 4–1 BIH
The agent called Switzerland (60%) — Worse than the model call right

The forecast below is what the agent published before kickoff.

Most likely scoreline
1–0 13.7%
60.2%
SUI win
22.7%
Draw
16.9%
BIH win
Top scorelines
  • 1–0 13.7%
  • 2–0 11.2%
  • 0–0 10.1%
  • 1–1 9.0%
Total goals
0 to 10 goals · most likely → tallest

The agent’s call

3-agent ensemble · deepseek-chat
SUI win
60.0%
Draw
24.0%
BIH win
16.0%

The model's prior of 58% home win is supported by Switzerland's squad value advantage (3x) and stronger key players like Xhaka and Embolo. Bosnia's recent form is steady but against weaker opposition, and their squad depth is inferior. The only head-to-head is too old to weigh. Conditions are neutral. I slightly nudge the home win up to 60% due to the squad quality gap and Amdouni's return, but Switzerland's recent underperformance tempers the move. Switzerland's expected goals (1.77) and Bosnia's (0.76) suggest a low-scoring match favoring the home side. The most likely scorelines are 1-0 and 2-0, reflecting Switzerland's defensive solidity and Bosnia's limited attack. Draw outcomes like 0-0 and 1-1 are possible if Switzerland's underperformance persists.

What the agent weighed
What the agent chose to investigate
The agent decided what to check on tavily — 9 sources kept:
  • “Switzerland squad injuries suspensions June 2026” SUI · 3 hits
    Late fitness or suspension news could change key player availability.
  • “Bosnia and Herzegovina squad injuries suspensions June 2026” BIH · 3 hits
    Late fitness or suspension news could change key player availability.
  • “Switzerland vs Bosnia and Herzegovina neutral venue Inglewood weather forecast June 18 2026” match · 3 hits
    Weather conditions (heat, rain) can affect playing style and stamina.
Agent scorelines
generated 2026-06-18
Last 5 — SUI
-0.76 pts/match vs model expectation · opp. avg #43
  • GER #7 -1.3
  • NOR #19 -0.3
  • JOR #75 +0.5
  • AUS #29 -0.9
  • QAT #87 -1.5
GF / GA last 10: 19 / 9
Last 5 — BIH
-0.11 pts/match vs model expectation · opp. avg #48
  • WAL #44 +0.1
  • ITA #13 +0.2
  • NOR #70 -0.7
  • PAN #72 -0.3
  • CAN #41 +0.2
GF / GA last 10: 15 / 11
Head-to-head (last 5)
  • 2016-03-29 Switzerland 0–2 Bosnia and Herzegovina
▸ Full score grid (7×7)
P(home goals × away goals), %
0
1
2
3
4
5
6
0
10.1
6.7
2.6
0.8
0.2
0.1
0.0
1
13.7
9.0
3.6
1.1
0.3
0.1
0.0
2
11.2
7.4
2.9
0.9
0.2
0.1
0.0
3
7.1
4.7
1.9
0.6
0.2
0.0
0.0
4
3.9
2.5
1.0
0.3
0.1
0.0
0.0
5
1.9
1.2
0.5
0.2
0.0
0.0
0.0
6
0.9
0.6
0.2
0.1
0.0
0.0
0.0

Rows = SUI goals; columns = BIH goals. Above-diagonal cells are home wins; diagonal = draws; below = away wins. Truncated at 6 — the joint mass past that is < 1 %.

Expected goals (Poisson rate, λ)
1.87
SUI
0.76
BIH

Independent-Poisson rates. W/D/L and the score grid integrate the full 13×13 joint under these two parameters.

News context — injuries, suspensions, projected XI — is not part of the model, which sees only past results.